Abstract

Grain segmentation on 3D superalloy images provides super- alloy’s micro-structures, based on which many physical and mechanical properties can be evaluated. This is a challenging problem in senses of (1) the number of grains in a superalloy sample could be thousands or even more; (2) the intensity within a grain may not be homoge- neous; and (3) superalloy images usually contains carbides and noises. Recently, the Multichannel Edge-Weighted Centroid Voronoi Tessel la- tion (MCEWCVT) algorithm [1] was developed for grain segmentation and showed better performance than many widely used image segmen- tation algorithms. However, as a general-purpose clustering algorithm, MCEWCVT does not consider possible prior knowledge from material scientists in the process of grain segmentation. In this paper, we ad- dress this issue by defining an energy minimization problem which sub- ject to certain constraints. Then we develop a Constrained Multichannel Edge-Weighted Centroid Voronoi Tessel lation (CMEWCVT) algorithm to effectively solve this constrained minimization problem. In particu- lar, manually annotated segmentation on a very small set of 2D slices are taken as constraints and incorporated into the whole clustering pro- cess. Experimental results demonstrate that the proposed CMEWCVT algorithm significantly improve the previous grain-segmentation perfor- mance.